MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Embedded Cypher knowledge graph for Python with a bundled MCP server and describe() schema for LLM agents
pypi MIT -
MCP server providing long-term memory for AI agents — knowledge graph with Qwen3 embeddings, continuous learning, and knowledge evolution
MIT ★ 6 -
Self-hosted agentic RAG for multi-repo code intelligence: real ASTs (Roslyn/TSC/Pyright) → semantic knowledge graph (SQLite + sqlite-vec) → SGC graph convolution → REST + embedded MCP server. Local embeddings, zero external APIs.
★ 1 -
memory-safegithub.com/eljoesb/memory-safeupdated this year
MCP memory server for Claude Code — knowledge graph in SQLite, local ONNX embeddings, token-budgeted retrieval
npm MIT -
Documentation RAG for coding agents: vector search, knowledge graph, agent memory, and an MCP server — torch-free local embeddings via fastembed
pypi Apache-2.0 ★ 1 -
A workload-adaptive agent memory system combining event logs, knowledge graphs, and vector embeddings
Apache-2.0 ★ 1 -
MegaMemorygithub.com/0xK3vin/MegaMemoryupdated this year
Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer.
MIT ★ 736 -
Neo4j knowledge graph MCP server with temporal versioning, semantic search, and vector embeddings for Claude AI
npm MIT ★ 1 -
🔌 Exposes RAG + Knowledge Graph over MCP — hybrid retrieval with vector embeddings + graph traversal. Citation-aware. MIT.
pypi MIT -
@shadowforge0/aquifer-memorygithub.com/shadowforge0/aquiferupdated this year
PG-native long-term memory for AI agents. Turn-level embedding, hybrid RRF ranking, optional knowledge graph. MCP server, CLI, and library API.
npm MIT -
Multi-language code knowledge graph in Rust — 21 languages via tree-sitter on LadybugDB, Cypher queries, semantic search (ONNX embeddings + BM25), taint & impact analysis, architecture diagram export, CI gates, 37 CLI commands + MCP server
NOASSERTION ★ 1 -
wrongsynapsegithub.com/ersinkoc/wrongsynapseupdated this year
Local-first Cognitive Memory Operating System and MCP server for autonomous AI coding agents. Tri-hybrid retrieval: ONNX semantic embeddings + SQLite FTS5/BM25 + hierarchical knowledge graph, fused with Reciprocal Rank Fusion. Zero cloud.
npm MIT -
Long-term memory for AI agents as an MCP server: typed records searched by meaning and a directed knowledge graph between projects. SQLite with sqlite-vec or PostgreSQL, in-process ONNX embeddings, one local HTTP server for every session.
nuget MIT -
A personal knowledge graph for Claude that survives across sessions, devices, and tools. Neo4j + semantic embeddings, OAuth-secured, single-user-by-default but multi-tenant-ready.
MIT ★ 2 -
MCP server for chat analysis using vector embeddings and knowledge graphs
pypi MIT License -
The most advanced MCP memory server. Hybrid search (BM25 + jina v5 embeddings + cross-encoder rerank), 100+ languages, temporal knowledge graph, finds any past Cursor or Claude conversation from a vague description, signed automatic updates. Pure Rust, single binary, 100% local, zero API calls.
NOASSERTION ★ 18 -
Config-schema-driven vector knowledge base: LanceDB storage, pluggable embedding/reranker/graph backends, CLI + HTTP REST + MCP (stdio & streamable HTTP)
cargo MIT OR Apache-2.0 -
Local-first knowledge base with hybrid search (vector + BM25) and knowledge graph, powered by embedded SurrealDB and BAAI/bge-m3 — exposed as MCP server and CLI
MIT -
Self-hosted temporal knowledge-graph memory for AI coding agents — Graphiti/Neo4j, MCP, local embeddings, retrieval eval harness
NOASSERTION -
factorforgegithub.com/aman9824/factorforgeupdated this year
Vectorless retrieval (no embeddings) over an evidence-linked knowledge graph, served as a standalone MCP server. Multi-agent Claude research pipeline.
MIT -
Turn a codebase into a deterministic AST knowledge graph (no embeddings, no LLM) and serve it over MCP, so coding agents ask the graph instead of grepping.
MIT -
knowledge-gungithub.com/akaddo97/knowledge-gunupdated this year
Generate paste-ready chatbot context bundles from a curated knowledge graph. Topic-scoped two-hop neighbourhood walker + hand-written intros. No vector RAG, no embedding cost, pure markdown. Pair with knowledge-gun-mcp to call from any MCP-aware LLM client.
MIT -
karp-word-graphgithub.com/souldriver007/karp-word-graphupdated this year
AI-powered KJV Bible study companion for Claude Desktop. Semantic scripture search, personal knowledge graph (study notes, prayers, insights), and passage study tools. Complete KJV pre-loaded (31,102 verses + 15,857 embeddings). MCP server by SoulDriver.
MIT -
Semantic knowledge graph navigation for Obsidian or markdown vaults using AI-powered vector embeddings and PostgreSQL+pgvector
MIT ★ 26 -
BrainAI — persistent memory for AI agents (Claude, Cursor, Codex): LightRAG knowledge graph + MCP, packaged as a macOS menu bar app. DeepSeek LLM, local bge-m3 embeddings.
MIT -
The Karpathy LLM Wiki, production-ready. Zero-RAG personal knowledge base with MCP server, multi-agent support, knowledge graph visualization, and hallucination enforcement. No embeddings, no vector DBs — just markdown + git.
★ 5 -
constellategithub.com/rjdscott/constellateupdated this year
Three knowledge planes (embedded, unified, composed) behind one retrieval contract, benchmarked head-to-head on MovieLens ml-25m. Relational, vector, and graph fusion, an MCP context plane with dual LLM drivers, and a React explorer.
MIT ★ 1 -
CLI + MCP for agent context: a task layer over TickTick, Notion, GitHub, Obsidian & more (RRF retrieval, provenance, reviewed writes, undo) plus a knowledge-graph layer — ats kg: facts from any source, human-ratified. Recommended engines: Graphiti (server), LadybugDB (embedded).
MIT ★ 17 -
Transform LinkedIn saved posts into an interactive, interconnected Obsidian knowledge graph. Features a zero-config web dashboard, hybrid LLM routing (Groq + local vLLM/llama.cpp), vector embeddings, and MCP support.
MIT -
@leanlabsinnov/codegraphgithub.com/cirilcetra/codegraphupdated this year
Live, queryable knowledge graph for your codebase. Indexes JS/TS into an embedded graph DB with embeddings and exposes an MCP server Claude Code and Cursor can call.
npm MIT -
book-braingithub.com/xjli1972/book-brainupdated this year
A GBrain-shaped knowledge brain over open-source / free books. Markdown on disk, SQLite + sqlite-vec hybrid search, typed graph edges, MCP server. TypeScript on Node + tsx, Ollama for local embeddings.
MIT ★ 5 -
MCP server giving LLM agents persistent memory: a SQLite knowledge graph with FTS5 search, tree-sitter code indexing (11 languages) with semantic code search, and optional server-side chunked embedding search with semantic, hybrid and MMR retrieval
cargo Apache-2.0 -
GraphMem-MCPgithub.com/Sathvik-1007/GraphMem-MCPupdated this year
Production-grade Graph-RAG MCP server with local embeddings — persistent knowledge graphs for any LLM-powered CLI agent
pypi MIT ★ 1 -
Atlasgithub.com/rohanps630/Atlasupdated this year
Local-first code knowledge graph & MCP server for AI coding agents — maps callers, cross-repo FE↔backend HTTP contracts, and impact across TypeScript, Go, Kotlin & Swift. No embeddings, no cloud.
MIT -
Dragon Brain — persistent long-term memory for AI agents via MCP (Model Context Protocol). Knowledge graph (FalkorDB) + vector search (Qdrant) + CUDA GPU embeddings. Works with Claude, Gemini CLI, Cursor, Windsurf, VS Code Copilot. 30 tools, 1121 tests.
MIT ★ 51 -
graphonomousgithub.com/c-u-l8er/graphonomousupdated this year
Continual learning MCP server for AI agents — topology-aware knowledge graph with kappa-routing, exposed as 5 loop-phase machines (retrieve/route/act/learn/consolidate), causal metadata, and neural embeddings. One of four MCP servers in the [&] three-prot
npm Apache-2.0 -
Knowledge Graph with Embeddings of Biomedical Ontologies for OMOP MCP servers and A2A workflows
MIT -
sciogengithub.com/ayanbag/sciogenupdated this year
Codebase intelligence layer — an embedded knowledge graph that makes call-graph and change-impact analysis instant.
pypi MIT -
ai-brain-mcpgithub.com/HenryCordes/ai-brain-mcpupdated this year
MCP server that turns a markdown knowledge vault into agent memory: search, read, link graph, and guarded capture. No embeddings, no vector DB.
MIT ★ 1 -
ctx-sysgithub.com/david-franz/ctx-sysupdated this year
Local hybrid RAG over a code knowledge graph. Indexes your codebase with tree-sitter + embeddings + a relationship graph and serves precise context to any AI assistant over MCP — fusing keyword (FTS5), vector, and graph search with reciprocal rank fusion. Local-first via Ollama; works with Claude Code, Cursor, and any MCP client.
MIT ★ 15 -
Local code knowledge graph for repos and multi-repo workspaces. Parses source with tree-sitter, fuses git co-change, docs, OpenTelemetry traces, and OpenAPI/GraphQL/Protobuf contracts into an embedded Badger store, then serves ranked symbol neighborhoods via CLI and an MCP server for IDEs and agents.
Apache-2.0 -
O_Owlgithub.com/smcozart/O_Owlupdated this year
Cognitive memory for AI agents. MCP server with 5 memory types, composite weight scoring, and a knowledge graph. SQLite as source of truth, Obsidian as the view layer. Embeddings run locally, no API keys.
★ 1 -
An intelligent code memory system that leverages vector embeddings, structured databases, and knowledge graphs to store, retrieve, and analyze code patterns with semantic search capabilities, quality metrics, and relationship modeling. Designed to enhance programming workflows through contextual recall of best practices, algorithms, and solutions.
MIT ★ 8 -
MemorizedMCP delivers a high‑performance, local‑first MCP Server in Rust that equips AI agents with an advanced hybrid memory system. It combines a knowledge graph, vector embeddings, and full‑text search with a novel documentary memory capability, enabling accurate recall of exact documents alongside rich semantic relationships.
MIT ★ 8 -
zaxygithub.com/syndicalt/zaxyupdated this year
Zaxy turns agent work into durable, auditable memory: a hash-chained Eventloom log as the source of truth, an embedded temporal knowledge graph for reasoning (local-first, no sidecar; Neo4j/Postgres optional), cited Memory Checkout for compact context, and MCP tools for model-facing retrieval, capture, and feedback.
MIT ★ 17 -
MCP server that gives Claude/Cursor a governed connection to your databases: builds a knowledge graph per DB (foreign keys, embeddings, glossary, query memory), hands the model only the relevant tables, read-only by default with confirmed developer writes and per-user audit. SQL Server, PostgreSQL, MySQL, SQLite, MongoDB, Cassandra.
-
**Persistent memory for AI agents that you can actually read.** Kybase stores what your agent learns as plain Markdown notes with `[[wikilinks]]`, searched by keyword and by meaning. It runs locally: notes live in an embedded Postgres on your machine (`~/.kybase`), with no Docker, no server and no account. **What your agent gets (18 tools)** - **Search** — `search_notes`: hybrid keyword + semantic search that returns the section each excerpt came from - **Read** — `get_note` (whole, windowed or one section), `list_notes`, `list_tags`, `list_folders`, `indexing_status` - **Write safely** — `create_note`, `append_to_note`, `replace_in_note`, `update_note` with conflict protection, `delete_note` / `restore_note` (trash) - **Link** — `get_backlinks`, `get_neighbors`, `get_graph` over the wikilink graph - **Organize** — `create_folder`, `update_folder`, `delete_folder` **Setup** Keyword search works right away. For search by meaning, pick an embedding provider in the settings: local **Ollama** (`ollama pull embeddinggemma`) keeps everything on your machine; **Google** or **OpenAI** need an API key and send note text to that provider. **Your data stays yours** `kybase-mcp export vault.zip` writes every note out as plain Markdown, folders as directories, readable in any editor, Obsidian included. **Want a UI?** The full Kybase app adds a web editor, a knowledge-graph view, share links, and one memory shared by Claude Code, claude.ai and Cursor: [github.com/Kyrzin/kybase](https://github.com/Kyrzin/kybase) Open source, AGPL-3.0.
smithery -
Corporate knowledge base exposed to AI assistants via an MCP server
-
YATS — Knowledge graph for AI coding agents. Cut code-reading tokens by 37–73%. Works with Codex, Claude, Copilot, Cursor & Gemini.
NOASSERTION -
mcp-memory-graphgithub.com/YonasValentin/mcp-memory-graphupdated this year
Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph in one SQLite file, $0/token, no cloud.
npm NOASSERTION ★ 2 -
swadbgithub.com/gsultani1/agentdbupdated this year
Sovereign agent memory system: tiered knowledge, knowledge graph, MCP-native, multi-agent.
pypi Apache-2.0 -
local-first temporal knowledge graph
pypi Apache-2.0 ★ 5 -
A growable, time-aware memory graph for AI agents. SQLite by default (zero runtime dependencies), Postgres optionally, configurable embeddings. JS API, CLI, MCP server, HTTP server.
npm MIT -
Local-first semantic knowledge graph
npm Apache-2.0 -
riggithub.com/anikolabs/rigactive
Local-first semantic knowledge graph with magnetic-pull retrieval
Apache-2.0 ★ 8 -
Graph-based retrieval for Obsidian vaults with Hebbian synaptic plasticity
MIT ★ 2 -
pmos-braingithub.com/feamando/brainupdated this year
Semantic Knowledge Graph with Graph Analytics, Event Sourcing, Enrichment Pipeline, Vector Search, MCP Server & Quality Scoring
pypi MIT -
A five-model knowledge graph over a directory you choose — built to prove itself wrong. SQLite + FTS5, stdlib-only, 100% local.
MIT -
MCP server that gives coding agents persistent project understanding via a knowledge graph
npm MIT -
Graph RAG for private codebases — index code into a knowledge graph with semantic search and MCP server. Self-hosted, no code leaves your machine.
npm MIT